Background: The aim of this study was to evaluate the impact of adverse lifestyle factors on outcomes in patients with human papillomavirus (HPV)-related oropharyngeal squamous cell carcinoma (OPSCC). Methods: From 2010 to 2019, 150 consecutive non-metastatic OPSCC patients receiving curative treatment in our institution were retrospectively enrolled. HPV positivity was defined as p16 expression ≥75%. The effects of adverse lifestyle factors on overall survival (OS) and disease-free survival (DFS) on OPSCC patients were determined. Results: The median follow-up duration was 3.6 years. Of the 150 OPSCCs, 51 (34%) patients were HPV-positive and 99 (66%) were HPV-negative. The adverse lifestyle exposure rates were 74.7% (n = 112) alcohol use, 57.3% (n = 86) betel grid chewing, and 78% (n = 117) cigarette smoking. Alcohol use strongly interacted with HPV positivity (HR, 6.00; 95% CI, 1.03–35.01), leading to an average 26.1% increased risk of disease relapse in patients with HPV-positive OPSCC. Heavy smoking age ≥30 pack-years was associated with increased risk of death (HR, 2.05; 95% CI, 1.05–4.00) and disease relapse (HR, 1.99; 95% CI, 1.06–3.75) in OPSCC patients. In stratified analyses, the 3-year absolute risk of disease relapse in HPV-positive OPSCC patients reached up to 50% when alcohol use and heavy smoking for ≥30 pack-years were combined. Conclusions: Alcohol acted as a significant treatment-effect modifier for DFS in HPV-positive OPSCC patients, diluting the favorable prognostic effect of HPV positivity. Heavy smoking age ≥30 pack-years was an independent adverse prognostic factor of OS and DFS in OPSCC patients. De-intensification treatment for HPV-related OPSCC may be avoided when these adverse lifestyle factors are present.

To provide precision medicine for better cancer care, researchers must work on clinical patient data, such as electronic medical records, physiological measurements, biochemistry, computerized tomography scans, digital pathology, and the genetic landscape of cancer tissue. To interpret big biodata in cancer genomics, an operational flow based on artificial intelligence (AI) models and medical management platforms with high-performance computing must be set up for precision cancer genomics in clinical practice. To work in the fast-evolving fields of patient care, clinical diagnostics, and therapeutic services, clinicians must understand the fundamentals of the AI tool approach. Therefore, the present article covers the following four themes: (i) computational prediction of pathogenic variants of cancer susceptibility genes; (ii) AI model for mutational analysis; (iii) single-cell genomics and computational biology; (iv) text mining for identifying gene targets in cancer; and (v) the NVIDIA graphics processing units, DRAGEN field programmable gate arrays systems and AI medical cloud platforms in clinical next-generation sequencing laboratories. Based on AI medical platforms and visualization, large amounts of clinical biodata can be rapidly copied and understood using an AI pipeline. The use of innovative AI technologies can deliver more accurate and rapid cancer therapy targets.

To evaluate whether adjusted computed tomography (CT) scan image-based radiomics combined with immune genomic expression can achieve accurate stratification of cancer recurrence and identify potential therapeutic targets in stage III colorectal cancer (CRC), this cohort study enrolled 71 patients with postoperative stage III CRC. Based on preoperative CT scans, radiomic features were extracted and selected to build pixel image data using covariate-adjusted tensor classification in the high-dimension (CATCH) model. The differentially expressed RNA genes, as radiomic covariates, were identified by cancer recurrence. Predictive models were built using the pixel image and immune genomic expression factors, and the area under the curve (AUC) and F1 score were used to evaluate their performance. Significantly adjusted radiomic features were selected to predict recurrence. The association between the significantly adjusted radiomic features and immune gene expression was also investigated. Overall, 1037 radiomic features were converted into 33 × 32-pixel image data. Thirty differentially expressed genes were identified. We performed 100 iterations of 3-fold cross-validation to evaluate the performance of the CATCH model, which showed a high sensitivity of 0.66 and an F1 score of 0.69. The area under the curve (AUC) was 0.56. Overall, ten adjusted radiomic features were significantly associated with cancer recurrence in the CATCH model. All of these methods are texture-associated radiomics. Compared with non-adjusted radiomics, 7 out of 10 adjusted radiomic features influenced recurrence-free survival. The adjusted radiomic features were positively associated with PECAM1, PRDM1, AIF1, IL10, ISG20, and TLR8 expression. We provide individualized cancer therapeutic strategies based on adjusted radiomic features in recurrent stage III CRC. Adjusted CT scan image-based radiomics with immune genomic expression covariates using the CATCH model can efficiently predict cancer recurrence. The correlation between adjusted radiomic features and immune genomic expression can provide biological relevance and individualized therapeutic targets.

Measuring bone mineral density (BMD) is important for surveying osteopenia in premature infants. However, the clinical availability of dual-energy X-ray absorptiometry (DEXA) for standard BMD measurement is very limited, and it is not a practical technique for critically premature infants. Developing alternative approaches for DEXA might improve clinical care for bone health. This study aimed to measure the BMD of premature infants via routine chest X-rays in the intensive care unit. A convolutional neural network (CNN) for humeral segmentation and quantification of BMD with calibration phantoms (QRM-DEXA) and soft tissue correction were developed. There were 210 X-rays of premature infants evaluated by this system, with an average Dice similarity coefficient value of 97.81% for humeral segmentation. The estimated humerus BMDs (g/cm³; mean ± standard) were 0.32 ± 0.06, 0.37 ± 0.06, and 0.32 ± 0.09, respectively, for the upper, middle, and bottom parts of the left humerus for the enrolled infants. To our knowledge, this is the first pilot study to apply a CNN model to humerus segmentation and to measure BMD in preterm infants. These preliminary results may accelerate the progress of BMD research in critical medicine and assist with nutritional care in premature infants.

Placental mesenchymal dysplasia (PMD) and partial hydatidiform mole (PHM) placentas share similar characteristics, such as placental overgrowth and grape-like placental tissues. Distinguishing PMD from PHM is critical because the former can result in normal birth, while the latter diagnosis will lead to artificial abortion. Aneuploidy and altered dosage of imprinted gene expression are implicated in the pathogenesis of PHM and also some of the PMD cases. Diandric triploidy is the main cause of PHM, whereas mosaic diploid androgenetic cells in the placental tissue have been associated with the formation of PMD. Here, we report a very special PMD case also presenting with trophoblast hyperplasia phenotype, which is a hallmark of PHM. This PMD placenta has a normal biparental diploid karyotype and is functionally sufficient to support normal fetal growth. We took advantage of this unique case to further dissected the potential common etiology between these two diseases. We show that the differentially methylated region (DMR) at NESP55, a secondary DMR residing in the GNAS locus, is significantly hypermethylated in the PMD placenta. Furthermore, we found heterozygous mutations in NLRP2 and homozygous variants in NLRP7 in the mother’s genome. NLRP2 and NLRP7 are known maternal effect genes, and their mutation in pregnant females affects fetal development. The variants/mutations in both genes have been associated with imprinting defects in mole formation and potentially contributed to the mild abnormal imprinting observed in this case. Finally, we identified heterozygous mutations in the X-linked ATRX gene, a known maternal–zygotic imprinting regulator in the patient. Overall, our study demonstrates that PMD and PHM may share overlapping etiologies with the defective/relaxed dosage control of imprinted genes, representing two extreme ends of a spectrum.

Prospective electrocardiography (ECG)-gated cardiac computed tomography angiography (CTA) is widely used for pediatric patients with congenital heart disease (CHD) due to the lower radiation dose compared with the ECG-gated technique. However, functional parameters acquired using ECG-gated cardiac CT to predict pulmonary hypertension (PH) in children with CHD have not yet been reported. This study aimed to investigate the potential of diastolic and systolic right ventricular diameters (RVD) on prospective ECG-gated cardiac CTA to predict PH in children with CHD. A total of 44 children with CHD were divided into two groups: CHD with PH (n = 22) and CHD without PH (n = 22). The association between ECG-gated CTA parameters and PH was evaluated by logistic regression. The receiver operating characteristic curve (ROC) was used to find the best cut-off point for the parameters measured by Youden's index. Patients with higher RVD-BSA [aOR (95% CI) diastolic: 2.76 (1.23-6.23); systolic: 6.15 (1.72-22.06)] had higher risk of PH after adjusting for age and patent ductus arteriosus. The area under the curve (AUC) of D-RVD-BSA was 0.907 and the AUC of S-RVD-BSA was 0.917. Logistic regression showed that patients with D-RVD-BSA over 6.86 or S-RVD-BSA over 5.87 had significantly higher risk of PH after adjustments (aOR = 23.52, 95% CI = 2.89-191.03; aOR = 31.14, 95% CI = 2.75-352.85). In conclusion, in children with CHD, measurements of diastolic or systolic BSA-modified RVDs on prospective ECG-gated CTA are non-invasive markers of PH. BSA-modified D-RVD of 6.86 or BSA-modified S-RVD of 5.87 may be used to identify PH in children with CHD.